Experiments in Linear Template Combination using Genetic Algorithms

TL;DR

This paper explores using genetic algorithms to efficiently combine templates for tactical natural language generation, aiming to improve sentence construction in an unsupervised, corpus-driven manner.

Contribution

It introduces a novel approach of applying genetic algorithms to optimize template sequences in an unsupervised NLG system, focusing on local grammaticality.

Findings

Baseline implementation produces gapped text

Genetic algorithms effectively explore template combinations

Method shows promise for unsupervised NLG

Abstract

Natural Language Generation systems typically have two parts - strategic ('what to say') and tactical ('how to say'). We present our experiments in building an unsupervised corpus-driven template based tactical NLG system. We consider templates as a sequence of words containing gaps. Our idea is based on the observation that templates are grammatical locally (within their textual span). We posit the construction of a sentence as a highly restricted sequence of such templates. This work is an attempt to explore the resulting search space using Genetic Algorithms to arrive at acceptable solutions. We present a baseline implementation of this approach which outputs gapped text.